Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1153 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Person Image Generation | Market-1501 (test) | 25 | Feb 26, 2026 | ||
| Classification | mfeat-pixel | 25 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 10-way 20-shot 76 | 25 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 10-way 10-shot 76 | 25 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 5-way 10-shot 76 | 25 | Feb 26, 2026 | ||
| Image Classification | CUBS | 25 | Feb 26, 2026 | ||
| Image Reconstruction | CIFAR-10 | 25 | Mar 10, 2026 | ||
| Domain Adaptation (Classification) | SVHN to MNIST | 25 | Feb 26, 2026 | ||
| Classification | PubMed 20 labels per class (test) | 25 | Feb 26, 2026 | ||
| Classification | Cora 20 labels per class (test) | 25 | Feb 26, 2026 | ||
| Factoid Question Answering | History factoid QA (test) | 25 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10+ (test) | 25 | Feb 26, 2026 | ||
| Bird's eye view object detection | KITTI (val) | 25 | Feb 26, 2026 | ||
| Natural Language Inference | MultiNLI mismatched (cross-domain) RepEval 2017 (test) | 25 | Feb 26, 2026 | ||
| Human Parsing | LIP (test) | 25 | Feb 26, 2026 | ||
| Abnormal event detection | UMN dataset | 25 | Feb 26, 2026 | ||
| Image De-raining | Synthesized Images (test) | 25 | Feb 26, 2026 | ||
| Unsupervised Domain Adaptation | SYN SIGNS to GTSRB (test) | 25 | Feb 26, 2026 | ||
| Age Estimation | ChaLearn (test) | 25 | Feb 26, 2026 | ||
| Multi-label Image Classification | MS-COCO (val) | 25 | Feb 26, 2026 | ||
| Text Classification | Amazon Review Full (test) | 25 | Mar 30, 2026 | ||
| Zero-Shot Action Recognition | HMDB51 (test) | 25 | Feb 26, 2026 | ||
| Age Estimation | Chalearn LAP 2015 (val) | 25 | Feb 26, 2026 | ||
| Dependency Parsing | CoNLL German 2009 (test) | 25 | Feb 26, 2026 | ||
| Image Retrieval | Holidays standard (test) | 25 | Feb 26, 2026 |